{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T10:20:08Z","timestamp":1773138008139,"version":"3.50.1"},"reference-count":68,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62402226"],"award-info":[{"award-number":["62402226"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62572171"],"award-info":[{"award-number":["62572171"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62441225"],"award-info":[{"award-number":["62441225"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62572244"],"award-info":[{"award-number":["62572244"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"publisher","award":["BK20241453"],"award-info":[{"award-number":["BK20241453"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Projects of Jiangsu Provincial Basic Research Program","award":["BK20253011"],"award-info":[{"award-number":["BK20253011"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["30924010817"],"award-info":[{"award-number":["30924010817"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Open Research Fund of National Mobile Communications Research Laboratory","award":["2024D07"],"award-info":[{"award-number":["2024D07"]}]},{"name":"National Key Laboratory for Novel Software Technology","award":["KFKT2024B17"],"award-info":[{"award-number":["KFKT2024B17"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Mobile Comput."],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1109\/tmc.2025.3632655","type":"journal-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:51:54Z","timestamp":1763146314000},"page":"5666-5682","source":"Crossref","is-referenced-by-count":0,"title":["AFedLF: Adaptive Layer Freezing of Foundation Models in Heterogeneous Federated Learning"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5553-5534","authenticated-orcid":false,"given":"Yue","family":"Zeng","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8073-2118","authenticated-orcid":false,"given":"Jie","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Computing, The Hong Kong Polytechnic University, Hung Hom, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9831-2202","authenticated-orcid":false,"given":"Song","family":"Guo","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong SAR, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1065-449X","authenticated-orcid":false,"given":"Baoliu","family":"Ye","sequence":"additional","affiliation":[{"name":"State Key Laboratory for Novel Software Technology, Department of Computer Science and Technology, Nanjing University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7538-1985","authenticated-orcid":false,"given":"Zhihao","family":"Qu","sequence":"additional","affiliation":[{"name":"College of Computer Science and Software Engineering, Hohai University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5689-382X","authenticated-orcid":false,"given":"Zicong","family":"Hong","sequence":"additional","affiliation":[{"name":"Department of Computing, The Hong Kong Polytechnic University, Hung Hom, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4577-8882","authenticated-orcid":false,"given":"Bin","family":"Tang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Software Engineering, Hohai University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3502-0146","authenticated-orcid":false,"given":"Jinyu","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Computing, The Hong Kong Polytechnic University, Hung Hom, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7734-4077","authenticated-orcid":false,"given":"Junlong","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2717-7566","authenticated-orcid":false,"given":"Jiaying","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1","article-title":"An image is worth 16 x 16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2020"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19-1423"},{"key":"ref3","first-page":"27706","article-title":"Pre-train your loss: Easy Bayesian transfer learning with informative priors","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Shwartz-Ziv","year":"2022"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2025.3553201"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3495243.3517017"},{"key":"ref6","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proc. AISTATS","author":"McMahan","year":"2017"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2025.3605765"},{"key":"ref8","first-page":"1","article-title":"Where to Begin? Exploring the impact of pre-training and initialization in federated learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Nguyen","year":"2023"},{"key":"ref9","article-title":"On the importance and applicability of pre-training for federated learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3361"},{"key":"ref11","article-title":"Conquering the communication constraints to enable large pre-trained models in federated learning","author":"Sun","year":"2022"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3552326.3587451"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"key":"ref14","first-page":"11285","article-title":"TinyTL: Reduce memory, not parameters for efficient on-device learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Cai","year":"2020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3352020.3352024"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3570361.3592505"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.2975749"},{"key":"ref18","article-title":"Federated learning with Non-IID data","author":"Zhao","year":"2018"},{"key":"ref19","first-page":"10351","article-title":"Towards understanding biased client selection in federated learning","volume-title":"Proc. AISTATS","author":"Cho","year":"2022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2021.3099723"},{"key":"ref21","first-page":"5132","article-title":"SCAFFOLD: Stochastic controlled averaging for federated learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Karimireddy","year":"2020"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3461852"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3492916"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2022.3214234"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3489642"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3552326.3567485"},{"key":"ref27","first-page":"19","article-title":"OORT: Efficient federated learning via guided participant selection","volume-title":"Proc. 15th USENIX Symp. Operating Syst. Des. Implementation","author":"Lai","year":"2021"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796935"},{"key":"ref29","first-page":"27504","article-title":"Resilient and communication efficient learning for heterogeneous federated systems","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"162","author":"Zhu","year":"2022"},{"key":"ref30","first-page":"8852","article-title":"DAdaQuant: Doubly-adaptive quantization for communication-efficient federated learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"H\u00f6nig","year":"2022"},{"key":"ref31","first-page":"2021","article-title":"FedPAQ: A communication-efficient federated learning method with periodic averaging and quantization","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Reisizadeh","year":"2020"},{"key":"ref32","article-title":"Federated Learning: Strategies for improving communication efficiency","author":"Kone\u010dn","year":"2016"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i6.20555"},{"key":"ref34","first-page":"1","article-title":"HeteroFL: Computation and communication efficient federated learning for heterogeneous clients","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Diao","year":"2021"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i4.20345"},{"key":"ref36","first-page":"3622","article-title":"QuPeD: Quantized personalization via distillation with applications to federated learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ozkara","year":"2021"},{"key":"ref37","first-page":"12876","article-title":"FjORD: Fair and accurate federated learning under heterogeneous targets with ordered dropout","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Horvath","year":"2021"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3166101"},{"key":"ref39","first-page":"23034","article-title":"ProgFed: Effective, communication, and computation efficient federated learning by progressive training","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang","year":"2022"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2025.3549600"},{"key":"ref41","article-title":"Transfer learning & fine-tuning","year":"2023"},{"key":"ref42","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Houlsby","year":"2019"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"ref44","article-title":"FreezeOut: Accelerate training by progressively freezing layers","author":"Brock","year":"2017"},{"key":"ref45","article-title":"AutoFreeze: Automatically freezing model blocks to accelerate fine-tuning","author":"Liu","year":"2021"},{"key":"ref46","article-title":"Accelerating deep learning inference via learned caches","author":"Balasubramanian","year":"2021"},{"key":"ref47","first-page":"69832","article-title":"Guiding the last layer in federated learning with pre-trained models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Legate","year":"2023"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS51616.2021.00010"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2023.3241965"},{"key":"ref50","first-page":"25","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu","year":"2022"},{"key":"ref51","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Simonyan","year":"2015"},{"key":"ref52","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref53","first-page":"1","article-title":"Fine-tuning can distort pretrained features and underperform out-of-distribution","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kumar","year":"2022"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583518"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i11.17155"},{"key":"ref56","article-title":"CoCo-FL: Communication-and computation-aware federated learning via partial NN freezing and quantization","author":"Pfeiffer","year":"2022"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00145"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-24777-7"},{"key":"ref59","article-title":"Plato: A new framework for federated learning research","year":"2022"},{"key":"ref60","first-page":"374","article-title":"Towards federated learning at scale: System design","volume-title":"Proc. Mach. Learn. Syst.","volume":"1","author":"Bonawitz","year":"2019"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.02611"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1264"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00447"},{"key":"ref66","article-title":"MobiPeRF: Mobile network measurement system","author":"Huang","year":"2011"},{"key":"ref67","article-title":"How many GB of smartphone storage do i need?","year":"2024"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16350"}],"container-title":["IEEE Transactions on Mobile Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7755\/11423852\/11248949.pdf?arnumber=11248949","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T20:01:27Z","timestamp":1773086487000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11248949\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":68,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tmc.2025.3632655","relation":{},"ISSN":["1536-1233","1558-0660","2161-9875"],"issn-type":[{"value":"1536-1233","type":"print"},{"value":"1558-0660","type":"electronic"},{"value":"2161-9875","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4]]}}}